*4.3. Limitations and Future Research*

Like all research, there are some limitations to this study. For example, there is no clearly defined relationship between the urbanization rate and GDP, and the urbanization rate is influenced by many factors [38,56]. To simplify the SD model, the equation parameters between the two can only be determined using regression analysis and referring to the development trend of other cities. In addition, adequate surveys involving stakeholders and local policy can also improve the rationality of the scenario simulation. However, this requires more comprehensive and in-depth preliminary research, which is also an aspect that can be considered for further studies.

In addition, only taking Zhaotong, a city located in southwest China, as a case study is far from enough. For planning problems in other cities with different geographical and natural endowments, the applicability of the model needs more work to be carried out to verify the model. Additionally, urban sustainability is a common issue around the world, but the solutions to different problems need to be contextualized in a variety of ways. Regardless of the approach taken, the rights of stakeholders should be considered when making decisions [57,58].

**Supplementary Materials:** The following supporting information can be downloaded at: https: //www.mdpi.com/article/10.3390/land11030411/s1, Table S1: Names, units and data sources of the variables included in the PLE space system dynamics model; Table S2: Comparison of simulated and real values of some key variables; Table S3: Cost Matrix for the 2015 simulation using 2010 PLE spatial distribution data; Table S4: Cost Matrix for the 2015 simulation using 2010 PLE spatial distribution data; Table S5: Confusion matrix between the actual and simulated values of PLE in 2015; Table S6: Confusion matrix between the actual and simulated values of PLE in 2018; Table S7: Cost Matrix for Base Scenario; Table S8: Cost Matrix for Scenario A1 and A2; Table S9: Cost Matrix for Scenario A3; Table S10: Cost Matrix for Scenario B1 and B2; Table S11: Cost Matrix for Scenario B3; Table S12: Cost Matrix for Scenario C1 and C2; Table S13: Cost Matrix for Scenario C3; Table S14: Ratio of land area for production, living and ecological space in 2010, 2015, and 2018; Table S15: Land area and percentage of 9 subclasses in PLE space in 2010, 2015, and 2018; Table S16: Land-use transition matrix from 2010 to 2015; Table S17: Land-use transition matrix from 2015 to 2018; Table S18: Projections of the economy and population under different scenarios in 2030; Table S19: Difference between future demand and allocated values for different scenarios; Figure S1: ROC curves and AUC values for 2010 suitability probability results based on ANN; Figure S2: ROC curves and AUC values for 2015 suitability probability results based on ANN.

**Author Contributions:** D.W.: conceptualization; methodology; validation; formal analysis; investigation; writing—original draft preparation; writing—review and editing; visualization. J.F.: conceptualization; writing—review and editing; supervision; project administration. D.J.: supervision; project administration; funding acquisition. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research was funded by the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA19040305), Youth Innovation Promotion Association (Grant No. 2018068). **Institutional Review Board Statement:** Not applicable.

**Informed Consent Statement:** Not applicable.

**Data Availability Statement:** Not applicable.

**Conflicts of Interest:** The authors declare no conflict of interest.
